Research map / Vision-language and multimodal / Cross-modal learning
Conflict-Aware Adaptive Cross-Reconstruction for Multimodal Sentiment Analysis
Yan Wang, Fuyuan Cao, Xingwang Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add cross-reconstruction module (CRM) (ablation) | CACR · CMU-MOSI | ACC7: 40.23 -> 48.69 | Improved |
| add conflict-aware weighting (CAW) instead of fixed weights of 1 (ablation) | CACR · CMU-MOSI | ACC7: 44.31 -> 48.69 | Improved |
| use CAW instead of generic adaptive gating weights (ablation) | CACR · CMU-MOSI | ACC7: 44.98 -> 48.69 | Improved |
| add fine-grained sentiment refinement (FSR) (ablation) | CACR · CMU-MOSI | ACC7: 46.79 -> 48.69 | Improved |
| add soft orthogonality loss Lo (ablation) | CACR · CMU-MOSI | ACC7: 40.96 -> 48.69 | Improved |
| add specific loss Lp (ablation) | CACR · CMU-MOSI | ACC7: 42.53 -> 48.69 | Improved |
| use stronger pretrained encoders (DeBERTa-large, MA-Net, wav2vec-large) (ablation) | CACR · CMU-MOSEI | ACC2: 85.37 -> 86.21 | Improved |
| use stronger pretrained encoders (DeBERTa-large, MA-Net, wav2vec-large) (ablation) | CACR · CMU-MOSI | ACC2: 87.04 -> 87.17 | No clear effect |
| vary omega_min, tau, alpha, beta hyper-parameters (ablation) | CACR · CMU-MOSI | ACC7 and MAE | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EMOE — EMOE: Modality-Specific Enhanced Dynamic Emotion Experts (CVPR 2025) · better on 4 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.87)
- Enriching Multimodal Sentiment Analysis Through Textual Emotional Descriptions of Visual-Audio Content (AAAI 2025 · similarity 0.86)
- A Multi-Focus-Driven Multi-Branch Network for Robust Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.86)
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.86)
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.85)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
